Comby vs Shebe

Comby is a free, open-source tool for searching and changing code structure with lightweight templates. It recognizes basic syntax in code, strings, and comments across many languages, with parsers listed for C/C++, C#, Go, Java, JavaScript, Python, Rust, Swift, and TypeScript, plus a generic matcher for other formats. The project targets large refactors and one-off changes, and an interactive review mode lets users inspect proposed edits. Comby can run from its command line, Python bindings, or HTTP requests sent to a server on your machine. Installation instructions cover macOS with Homebrew, Ubuntu, Windows through Ubuntu on WSL, and Docker; building from source is also described. Linked projects include an Emacs package and a prototype VS Code extension. Other uses include structural code search, compiler fuzzing, test-case reduction, editor find and replace, and academic research. Comby matches balanced delimiters while accounting for comments and string literals, and supports regex search. It is self-hosted and available for API, Linux, macOS, and Windows use. The Apache-2.0 license is identified in the public repository.

Shebe is a local code-search tool that uses BM25 full-text search across code repositories. It ranks results and supports phrase searches, Boolean queries, and literal matching. Fourteen MCP tools serve coding agents with functions including search, repository indexing, file reading, and reference finding. Shebe runs without embeddings, a GPU, or a cloud service, but repositories must be cloned locally before indexing; remote repository URLs are not supported. Its text-based search does not provide semantic similarity, so related words such as “login” and “authenticate” may not match. Prebuilt binaries are listed for Linux x86_64 and macOS on Apple Silicon and Intel; Linux ARM64 is planned. Windows users need to build it from source. The installation guide covers MCP setup and Zed configuration and points to the organization for VS Code and other editor extensions. Shebe is free and licensed under Apache-2.0. The README reports 2 ms query latency and indexing rates from 1,928 to 11,210 files per second in its listed benchmarks.